ai: list custom GGUF files in the Manage tab

A GGUF copied into ai/models/ by hand could be activated by editing
ai.yaml, but never appeared in the Manage tab because the catalog
endpoint only returned CDN/bundled models. The Active Model dropdown
builds from downloaded models, so a custom file was unselectable.

The catalog endpoint now merges any on-disk *.gguf that is not in the
catalog as a `custom` tier model with its real size and no URL. It is
discovered on every request, so a file appears the next time the page
loads; the file refresh is not involved and does not index models.

Catalog models are never duplicated and in-progress .tmp downloads are
ignored. Custom rows read "On disk" and the hint explains the copy-in
path, the tool-calling requirement, and the context_size fallback.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

app/src/components/Ai.js

@@ -26,7 +26,9 @@ export function AiModelRow({model, onDownload}) {
         <Table.Cell>{humanFileSize(size)}</Table.Cell>
         <Table.Cell>
             {downloaded
-                ? <Button size='xs' icon='check' disabled role='save'>Downloaded</Button>
+                ? <Button size='xs' icon='check' disabled role='save'>
+                    {tier === 'custom' ? 'On disk' : 'Downloaded'}
+                </Button>
                 : <APIButton size='xs' icon='download' color='violet' onClick={() => onDownload(model)}>
                     Download
                 </APIButton>}
@@ -184,6 +186,10 @@ export function ManageAi() {
             <p>The AI assistant runs entirely on this WROLPi — no internet is needed after a model
                 is downloaded. Download a model, select it, then enable the assistant. Monitor
                 download progress on the <b>Downloads</b> page.</p>
+            <p>You can also copy your own GGUF file into <b>ai/models/</b>; it will appear here as a
+                <b>custom</b> model the next time this page loads. The model must support tool calling
+                (Qwen3, Llama 3.x, and Mistral instruct models do). Custom models use the default
+                context size unless you set <b>context_size</b> in <b>ai.yaml</b>.</p>
         </InfoMessage>
     </>;
 }

app/src/components/Ai.test.js

@@ -104,6 +104,24 @@ describe('ManageAi', () => {
         await waitFor(() => expect(postAiSettings).toHaveBeenCalledWith({enabled: true}));
     });
 
+    it('lists a custom GGUF from ai/models in the Active Model dropdown', async () => {
+        const custom = {
+            name: 'My-Custom-Model-Q8_0.gguf', tier: 'custom', size: 3_000_000_000, url: null,
+            description: 'Custom model found in ai/models/. Not from the WROLPi catalog.',
+            downloaded: true, active: false,
+        };
+        const fixture = catalogFixture();
+        getAiCatalog.mockResolvedValue({...fixture, models: [...fixture.models, custom]});
+        render(<ManageAi/>);
+        await waitFor(() => expect(screen.getByText('On disk')).toBeInTheDocument());
+        expect(screen.getByRole('cell', {name: 'custom'})).toBeInTheDocument();
+
+        fireEvent.click(screen.getByRole('textbox', {name: 'Active Model'}));
+        const option = await screen.findByRole('option', {name: 'My-Custom-Model-Q8_0.gguf'});
+        fireEvent.click(option);
+        await waitFor(() => expect(postAiSettings).toHaveBeenCalledWith({active_model: 'My-Custom-Model-Q8_0.gguf'}));
+    });
+
     it('shows the slow-hardware warning on a Pi 4', async () => {
         getAiCatalog.mockResolvedValue(catalogFixture({slow_hardware: true}));
         render(<ManageAi/>);

modules/ai/api.py

@@ -740,12 +740,26 @@ async def read_content(request: Request, file_group_id: int):
 async def manage_catalog(_: Request):
     models, source = await catalog.get_models_catalog()
     models_directory = catalog.get_models_directory()
-    downloaded = {i.name for i in models_directory.glob('*.gguf')} if models_directory.is_dir() else set()
+    on_disk = {i.name: i for i in models_directory.glob('*.gguf')} if models_directory.is_dir() else dict()
     disk_usage = sum(i.stat().st_size for i in models_directory.glob('*')) if models_directory.is_dir() else 0
 
     config = get_ai_config()
-    models = [dict(i, downloaded=i['name'] in downloaded, active=i['name'] == config.active_model)
+    models = [dict(i, downloaded=i['name'] in on_disk, active=i['name'] == config.active_model)
               for i in models]
+    # Any GGUF the user copied into ai/models themselves is a "custom" model.  It is discovered
+    # here on every request (no file refresh) so it appears in the Active Model dropdown.
+    catalog_names = {i['name'] for i in models}
+    for name, path in sorted(on_disk.items()):
+        if name not in catalog_names:
+            models.append(dict(
+                name=name,
+                tier='custom',
+                url=None,
+                size=path.stat().st_size,
+                description='Custom model found in ai/models/. Not from the WROLPi catalog.',
+                downloaded=True,
+                active=name == config.active_model,
+            ))
 
     total_ram = catalog.get_total_ram_bytes()
     return json_response(dict(

modules/ai/test/test_config_catalog.py

@@ -192,3 +192,39 @@ async def test_manage_settings_adopts_model_context(async_client, test_directory
     content = dict(active_model='Qwen3-4B-Instruct-2507-Q4_K_M.gguf', context_size=4_096)
     request, response = await async_client.post('/api/ai/manage/settings', content=json.dumps(content))
     assert response.json['context_size'] == 4_096
+
+
+@pytest.mark.asyncio
+async def test_manage_catalog_lists_custom_models(async_client, test_directory, test_ai_config):
+    """A GGUF the user copied into ai/models (not from the catalog) is listed as a custom model so it
+    can be selected in the Manage tab.  It is discovered on every request; no file refresh needed."""
+    models_dir = test_directory / 'ai/models'
+    models_dir.mkdir(parents=True)
+    (models_dir / 'My-Custom-Model-Q8_0.gguf').write_bytes(b'GGUF' * 10)
+    (models_dir / 'Qwen3-1.7B-Q4_K_M.gguf').write_bytes(b'GGUF')
+    (models_dir / 'partial.gguf.tmp').write_bytes(b'x')  # an in-progress download is not a model
+
+    with mock.patch('modules.ai.catalog.fetch_models_manifest', side_effect=RuntimeError('offline')):
+        request, response = await async_client.get('/api/ai/manage/catalog')
+    assert response.status_code == HTTPStatus.OK
+    names = [i['name'] for i in response.json['models']]
+    assert names.count('Qwen3-1.7B-Q4_K_M.gguf') == 1, 'catalog model must not be duplicated'
+    assert 'partial.gguf.tmp' not in names
+
+    custom = next(i for i in response.json['models'] if i['name'] == 'My-Custom-Model-Q8_0.gguf')
+    assert custom['tier'] == 'custom'
+    assert custom['downloaded'] is True
+    assert custom['active'] is False
+    assert custom['size'] == 40
+    assert custom['url'] is None
+
+    # It can be activated like any downloaded model; it has no catalog context default.
+    content = dict(active_model='My-Custom-Model-Q8_0.gguf')
+    request, response = await async_client.post('/api/ai/manage/settings', content=json.dumps(content))
+    assert response.status_code == HTTPStatus.OK
+    assert response.json['active_model'] == 'My-Custom-Model-Q8_0.gguf'
+    assert response.json['context_size'] is None
+    with mock.patch('modules.ai.catalog.fetch_models_manifest', side_effect=RuntimeError('offline')):
+        request, response = await async_client.get('/api/ai/manage/catalog')
+    custom = next(i for i in response.json['models'] if i['name'] == 'My-Custom-Model-Q8_0.gguf')
+    assert custom['active'] is True